1 City

2 County

3 Employment Projections

# add geom_hline showing "Total media wages"
# # Change the "horizontal justification" to be left-justified with hjust 

mycols <- c("blue", "red")
ggplot(data=occupation, mapping=aes(x=industry, y=median_wages17, fill=compu)) +
  stat_summary(fun.y=mean, geom="bar") +
  scale_y_continuous(labels=dollar) +
  labs(title="Median Wages by Industry in 2017", x="", y="") + 
  coord_flip() + 
  theme(legend.position="none") + 
  scale_fill_manual(values=mycols) + 
  geom_text(aes(label = median_wages17), color = "black", hjust=-0.1) +
  geom_hline(yintercept = 37690, color="red", size=1, linetype="dashed")

# remove all occupations

occupation <- occupation[2:23,]

occupation$industry <- fct_reorder(occupation$industry, occupation$change2026, mean, na.rm=TRUE)
ggplot(data=occupation, mapping=aes(x=industry, y=change2026, fill=compu)) +
  stat_summary(fun.y=mean, geom="bar") +
  scale_y_continuous() +
  labs(title="Employment Jobs Growth Projection by Industry 2016-2026 ", x="", y="") + 
  coord_flip() + 
  theme(legend.position="none") + 
  scale_fill_manual(values=mycols) + 
  geom_text(aes(label = change2026), color = "black", hjust=-0.1) 

  # geom_hline(yintercept = 37690, color="red", size=1, linetype="dashed")

occupation$industry <- fct_reorder(occupation$industry, occupation$perchange206, mean, na.rm=TRUE)

ggplot(data=occupation, mapping=aes(x=industry, y=perchange206, fill=compu)) +
  stat_summary(fun.y=mean, geom="bar") +
  scale_y_continuous() +
  labs(title="% Employment Growth Projection by Industry 2016-2026 ", x="", y="") + 
  coord_flip() +
  theme(legend.position="none") +
  scale_fill_manual(values=mycols) +
  geom_text(aes(label = perchange206), color = "black", hjust=-0.1)

rm(mycols)

2017 Employment by major occupational group, 2016 and projected 2026 (Numbers in thousands) [1]. Tech employees are compensated nicely due to this tech boom. For example, in 207 while the annual medialn wage for all occupations was $37,000 in the U.S., it was $84,600 for the computer occupations, second only to $102,000 of the management occupations as shown in Table 1.

4 Dinamic Visualizations

5 Maps

# Tech
# Set zero margins in plot window, so that map fits
par(mar=c(0,0,0,0))
# plot(zips.shp, lwd=0.1)

# One dot per 10 people
plotvar <- df.17$tech/10

# Calculated random dots for each zip code and store the coordinates in cadots.rand
cadots.rand <- dotsInPolys(zips.shp, as.integer(plotvar), f="random")

# Plot a specific region - zooms in LA conty
plot(zips.shp, lwd=0.1, xlim=c(-118.510000,-117.820000), ylim=c(33.710000,34.860000))
plot(cadots.rand, add=T, pch=19, cex=0.1, col="#000080", border="red") # Blue ---- "#09900d" Green

# Info
# Set zero margins in plot window, so that map fits
# par(mar=c(0,0,0,0))
# # plot(zips.shp, lwd=0.1)
# 
# # One dot per 10 people
# plotvar1 <- df.17$info/10
# 
# # Calculated random dots for each zip code and store the coordinates in cadots.rand
# cadots.rand <- dotsInPolys(zips.shp, as.integer(plotvar1), f="random")
# 
# # Plot a specific region - zooms in LA conty
# plot(zips.shp, lwd=0.1, xlim=c(-118.510000,-117.820000), ylim=c(33.710000,34.860000))
# plot(cadots.rand, add=T, pch=19, cex=0.1, col="#8B0000", border="red") # Blue ---- "#09900d" Green # #8B0000 Red # #FF4500 Orange

# Professional 
# Set zero margins in plot window, so that map fits
# par(mar=c(0,0,0,0))
# # plot(zips.shp, lwd=0.1)
# 
# # One dot per 10 people
# plotvar2 <- df.17$prof/10
# 
# # Calculated random dots for each zip code and store the coordinates in cadots.rand
# cadots.rand <- dotsInPolys(zips.shp, as.integer(plotvar2), f="random")
# 
# # Plot a specific region - zooms in LA conty
# plot(zips.shp, lwd=0.1, xlim=c(-118.510000,-117.820000), ylim=c(33.710000,34.860000))
# plot(cadots.rand, add=T, pch=19, cex=0.1, col="#FF4500", border="red") # Blue ---- "#09900d" Green # #8B0000 Red # #FF4500 Orange

rm(plotvar)
rm(cadots.rand)
rm(cacounties)
rm(cacounties.shp)
rm(cnty.zips)
rm(cnty.zips.17)

2017 Dot density zip code map
Each dot = 10 tech jobs

# install imageMagick
# https://www.imagemagick.org/script/download.php#windows

# Tutorials
# https://ryanpeek.github.io/2016-10-19-animated-gif_maps_in_R/
# https://cran.r-project.org/web/packages/magick/vignettes/intro.html

# library(magick) # this is call to animate/read pngs

# save all png files to path folder

# create gif
# list.files(path = "C:/Users/joao_/Downloads/Gif/", pattern = "*.png", full.names = T) %>%
#   map(image_read) %>% # reads each path file
#   image_join() %>% # joins image
#   image_animate(fps=100) %>% # animates, can opt for number of loops
#   image_write("tech_100.gif") # write to current dir

6 Correlation Between the CHCI and the Median House Income of Los Angeles County Zip Codes

Fig. 8 shows the association between the 2012 CHCI and the 2016 median household income of 282 zip codes in L.A. County. We can see a very strong correlation correlation between the human capital level [23] and the household income for the zip code in L.A. It demonstrates the importance to invest in education (chci) in order to create more productive workforce and more high paying jobs.

# Adds Title / Lables
p5 = p4+
scale_x_continuous(name = "City Human Capital Index (CHCI)")+
scale_y_continuous(name = "Log Income, 2016") +
ggtitle("CHCI and Median Income Per Zip Code")
p5

## Warning: Removed 7 rows containing non-finite values (stat_smooth).

## Warning: Removed 7 rows containing missing values (geom_point).

## Warning: Removed 7 rows containing missing values (geom_point).

## Warning: Removed 7 rows containing missing values (geom_text_repel).

################

## Need to clean code bellow

# str(df.17)
# df.17$GEOID <- as.factor(df.17$GEOID)
# names(masterzip) <- c("GEOID", "name")
# z <- inner_join(df.17, masterzip, by = "GEOID")
# str(z)
# top_zip <- z %>% arrange(desc(per)) %>% top_n(20, wt=per)
# 
# names(top_zip) <- c("zip", "V1",    "year",  "tech",  "info",  "prof",  "per",   "total", "name")
# str(cor)
# str(top_zip)
# top_zip$zip <- as.numeric(top_zip$zip)
# 
# cor <- inner_join(top_zip, cor, by="zip")
################
# NEW

# Create the scatter plot with regression line
# 
# p7 <- ggplot(cor, aes(x=chci, y=estimate)) +
#   geom_point(colour = "blue", size=4) +
#   labs(title = "Fig. 8 ",
#        x = "City Human Capital Index", y = "Median Household Income ($)") +
#   scale_x_continuous(limits = c(85, 175)) +
#     geom_smooth(colour = "red", method=lm,   # Add linear regression line
#               se=FALSE)    # Don't add shaded confidence region
# p7

# p1 <- ggplot(cor, aes(x=chci, y=log(estimate)))+
#   geom_point(colour = "red")
# p1
# p2 <- p1 +
#   geom_smooth(mapping = aes(linetype = "r2"),
#               method = "lm",
#               formula = y ~ x , se = FALSE,
#               color = "black")
# p2 + geom_point()
# p2 + geom_point(shape = 1, size = 2) # Changes to shape = 1
# p3=p2 + geom_point(shape = 1, size = 3, stroke=1.5)
# p3
# # Labels overlap - use ggrepel
# # install.packages("ggrepel") 
# library("ggrepel") # Repel overlapping text labels away from each other.
# p4 <- p3 + geom_text_repel(aes(label = zip), size=2) # Uses greppel text repel
# p4



# Adds Title / Lables
# p5 = p4+
# scale_x_continuous(name = "Capital Human City Index")+
# scale_y_continuous(name = "Log Income, 2016") +
# ggtitle("CHCI and Median Income Per Zip Code")
# p5
# 
# summary(cor)
# chci media 163

################
# str(df.17)
# df.17$GEOID <- as.factor(df.17$GEOID)
# names(masterzip) <- c("GEOID", "name")
# z <- inner_join(df.17, masterzip, by = "GEOID")
# str(z)
# top_zip <- z %>% arrange(desc(per)) %>% top_n(30, wt=per)
# str(cor)
# str(top_zip)


# # Creates vector with list of top tech zip codes
# top_zip$GEOID -> zip.label
# 
# # Only shows labels from list created
# 
# library(ggplot2)
# library(readxl) 
# library(tidyverse) # Includes ggplot2
# library(dplyr)
# 
# p6 = p5 + geom_text(aes(label = zip),
#             color = "gray20", data = filter(cor, cor$zip %in% zip.label))
# p6
# 
# 
# p4 = p3 + geom_text(aes(label = Country),
#             color = "gray20", data = filter(cpigdp, Country %in% country.label))

7 Conclusions

• coming soon …

8 References

1. [1] Assumptions Tech industry employment was calculated using the following: (1) Information jobs (NAICS: 51), and (2) Professional, Scientific, & Technical Skills (NAICS: 54). Data source: Quarterly Census of Employment and Wages (QCEW) developed through a cooperative program between the states and the U.S. Bureau of Labor Statistics.– These data are summarized by Industry Sector (2-digit NAICS).
2. [2] https://www.bls.gov/emp/tables/emp-by-major-occupational-group.htm
3. [3] Dowload shape files for county from LA Data Portal https://data.lacity.org/ Los Angeles Open Data
4. [4] https://data.lacounty.gov/Geospatial/ZIP-Codes/65v5-jw9f
5. [5] ACS

24. [x] http://www.anderson.ucla.edu/centers/ucla-anderson-forecast/projects-and-partnerships/city-human-capital-index

9 Acknowledgements

• This project was largely inspired by conversations with Dr. William Yu, UCLA
• Dynamic Visualizations were inspire by Google Public Data Explorer.

# install.packages("kableExtra")
# 
# library(kableExtra)
# 
# kable(df.17)
# 
# # The code below will automatically include the image in the rmarkdown document
# kable(dt, "latex", booktabs = T) %>%
# column_spec(1, bold = T) %>%
# kable_as_image()